DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to run a local OpenAI-compatible Qwen3.8-27B server with Halogen Server

Start the halogen container on Strix Halo and call a local chat endpoint on port 8731.

Short answer: Install the Hugging Face CLI with pip install -U "huggingface_hub[cli]"; then download the weights and tokenizer with hf download peonist-ai/halogen-qwen3.8-27b --local-dir ~/halogen-models. All steps.

Who it is forA developer with an AMD Strix Halo machine who wants a private, local Qwen3.8-27B endpoint for their own apps or scripts.

The problemRunning a 27B model locally needs a serving setup tuned to the GPU, and generic runtimes do not target this hardware.

The outcomeAn OpenAI-compatible chat endpoint answers requests on localhost port 8731 using the Qwen3.8-27B checkpoint.

What you need first

  • AMD Strix Halo machine (Radeon 8060S class GPU, gfx1151) with /dev/kfd and /dev/dri available
  • Podman (or Docker with the video and render group flags described in the README)
  • About 36 GB of free disk for the 35.9 GB checkpoint, plus the 3.5 GB image
  • Python with pip to install the Hugging Face CLI

Steps

  1. Install the Hugging Face CLI with pip install -U "huggingface_hub[cli]".
  2. Download the weights and tokenizer with hf download peonist-ai/halogen-qwen3.8-27b --local-dir ~/halogen-models. (inferred, check the README)
  3. Start the server with podman run --rm -p 8731:8731 --device /dev/kfd --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined --ipc=host -v ~/halogen-models:/models:ro -v ~/halogen-models/tokenizer:/tokenizer:ro ghcr.io/peonist-ai/halogen:0.1.4. (inferred, check the README)
  4. Send a chat request with curl to http://localhost:8731/v1/chat/completions using a JSON body with a messages list. (inferred, check the README)
  5. Read the reply's content field, and check finish_reason before trusting the answer.

Prompt for your agent

In the repo peonist-ai/halogen-server, start the ghcr.io/peonist-ai/halogen:0.1.4 container with the checkpoint directory at <models_path> and the tokenizer at <models_path>/tokenizer, then send the prompt <prompt> to http://localhost:8731/v1/chat/completions. Expected output: a chat completion JSON with a non-empty message content. Verify that finish_reason is not "length".

Caveat. The model weights are licensed separately from the engine by their original authors, and the image works only on Strix Halo (gfx1151) hardware.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for peonist-ai/halogen-server and "Run a local OpenAI-compatible Qwen3.8-27B server"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer